© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 159634
    Prev
    Next
    INDEX
    Explanations

    places and people

    np_acts-logits-general · gemini-2.5-flash-lite

    explaining "why" or "means"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hátsó
    0.54
     ETFs
    0.51
     Tetapi
    0.51
     horaires
    0.51
     trasero
    0.51
    បន្ថ
    0.50
    酆
    0.50
     emberek
    0.49
     arbete
    0.48
     amikor
    0.48
    POSITIVE LOGITS
    ા
    0.44
    iano
    0.44
    ían
    0.44
    (
    0.43
    ∝
    0.43
    venues
    0.42
    designated
    0.42
    riminate
    0.42
    ią
    0.41
    a
    0.41
    Activations Density 0.000%

    No Known Activations